JetBrains has introduced the launch of its new AI coding agent, Junie. Junie runs inside JetBrains IDEs and might tackle easy coding duties or help on extra advanced duties with collaboration from the developer.
“Because of the facility of JetBrains IDEs, coupled with dependable LLMs, Junie already solves duties that may in any other case require hours of labor,” Andrew Zakonov, product chief at JetBrains, wrote in a weblog publish.
Builders can share prompts with the agent, evaluate the outcomes, and modify as wanted. Over time, it learns the context of code and the developer’s preferences and elegance. “This ends in higher code high quality and management on how Junie performs duties, making certain reliability, making Junie a trusted collaborator in your workforce,” Zakonov wrote.
RELATED: AI brokers are reworking the software program growth life cycle
It will probably additionally run code and assessments, and might verify the mission state after making modifications to confirm that every one assessments have handed. “AI-generated code may be simply as flawed as developer-written code. In the end, Junie is not going to simply pace up growth – it’s poised to boost the bar for code high quality,” mentioned Zakonov.
Junie was capable of resolve 53.6% of duties on a single run in accordance with the SWEBench Verified benchmark, which incorporates 500 developer duties. In response to JetBrains, this proves that’s able to adapting to the wants of at this time’s builders.
In response to JetBrains, Junie doesn’t run domestically, because it makes use of OpenAI and Anthropic fashions. There’s presently a waitlist for the Early Entry Program, and it’s initially out there in IntelliJ IDEA Final and PyCharm Skilled, with assist for WebStorm coming subsequent. It is just out there on OS X and Linux in the mean time.
